LLM SHOWDOWN
LLM SHOWDOWN
LLM Showdown is a 2-round event of wit, strategy, and AI prompting inspired by Codenames. Two teams compete to guide ChatGPT toward their secret target word without ever revealing it directly. Players must craft clever, indirect prompts while avoiding the target word and all its derivatives. Every response becomes a test of deduction, deception, and prompt-engineering skill.
Secure Your Spot
Limited seats available.
- 1st Prize
- ₹ 5000
- 2nd Prize
- ₹ 3000
- 3rd Prize
- ₹ 2000
Event Heads
ITEvent Round Details
Each team is assigned 5 secret target words by the Judge. Teams must craft a prompt that subtly leads ChatGPT to talk around the opponent's target words. No root word or derivatives of the target term may be used. All prompts are executed using the designated ChatGPT device provided. The goal is to: Make ChatGPT respond relevantly, without being too obvious. Prevent the opponent from correctly guessing your assigned word. In the guessing phase, the teams will be handed a word bank with a 100 words from which they would have to find the answers to the 5 riddles given. If they guess the wrong word, the points will be given to the team which the word (wrongly guessed) actually belongs to. The prompt should be interpretable by the LLM but misleading enough that the opponent cannot guess the target word.
- Teams can join anytime during this round.
- Flexible entries: Any team arriving during this window can participate.
- Each team plays one match, facing another team.
- Judges maintain scores for each team based on a scoring rubric.
- Top 4 teams with the highest cumulative scores progress to the Final Rounds.
- Time Limits:
- 10 minutes for prompt crafting
- 5 minutes for the opponent's guessing
The scores for each of the teams are evaluated on the basis of the criteria decided, which includes Prompt Quality, LLM Interpretability, Deceptiveness, Opponent's guess, Clarity and Style, in case of a Tie, the team with higher LLM Interpretability score wins.
In the Final Rounds, each team must incorporate a randomly drawn "Power Prompt Twist Card" into their crafted prompt. Examples of twists: Use a pun in your prompt Include a metaphor involving space Prompt must be exactly 25 words Prompt must be phrased as a question Prompt must rhyme This twist increases difficulty and forces teams to think creatively. Successfully integrating the twist without compromising deception or clarity is now a part of the judging criteria.
- Semifinal 1: Top Seed vs 4th Seed
- Semifinal 2: 2nd Seed vs 3rd Seed
- Grand Finale: Winners of both semifinals face off
- Failing to adhere to the condition in Power Prompt Twist card impacts scoring under "Prompt Quality".
The scores for each of the teams are evaluated on the basis of the criteria decided, which includes Prompt Quality, LLM Interpretability, Deceptiveness, Opponent's guess, Clarity and Style, in case of a Tie, the team with higher LLM Interpretability score wins.
ITLLM SHOWDOWN
LLM SHOWDOWN
LLM Showdown is a 2-round event of wit, strategy, and AI prompting inspired by Codenames. Two teams compete to guide ChatGPT toward their secret target word without ever revealing it directly. Players must craft clever, indirect prompts while avoiding the target word and all its derivatives. Every response becomes a test of deduction, deception, and prompt-engineering skill.
Secure Your Spot
Limited seats available.
- 1st Prize
- ₹ 5000
- 2nd Prize
- ₹ 3000
- 3rd Prize
- ₹ 2000
Event Round Details
Each team is assigned 5 secret target words by the Judge. Teams must craft a prompt that subtly leads ChatGPT to talk around the opponent's target words. No root word or derivatives of the target term may be used. All prompts are executed using the designated ChatGPT device provided. The goal is to: Make ChatGPT respond relevantly, without being too obvious. Prevent the opponent from correctly guessing your assigned word. In the guessing phase, the teams will be handed a word bank with a 100 words from which they would have to find the answers to the 5 riddles given. If they guess the wrong word, the points will be given to the team which the word (wrongly guessed) actually belongs to. The prompt should be interpretable by the LLM but misleading enough that the opponent cannot guess the target word.
- Teams can join anytime during this round.
- Flexible entries: Any team arriving during this window can participate.
- Each team plays one match, facing another team.
- Judges maintain scores for each team based on a scoring rubric.
- Top 4 teams with the highest cumulative scores progress to the Final Rounds.
- Time Limits:
- 10 minutes for prompt crafting
- 5 minutes for the opponent's guessing
The scores for each of the teams are evaluated on the basis of the criteria decided, which includes Prompt Quality, LLM Interpretability, Deceptiveness, Opponent's guess, Clarity and Style, in case of a Tie, the team with higher LLM Interpretability score wins.
In the Final Rounds, each team must incorporate a randomly drawn "Power Prompt Twist Card" into their crafted prompt. Examples of twists: Use a pun in your prompt Include a metaphor involving space Prompt must be exactly 25 words Prompt must be phrased as a question Prompt must rhyme This twist increases difficulty and forces teams to think creatively. Successfully integrating the twist without compromising deception or clarity is now a part of the judging criteria.
- Semifinal 1: Top Seed vs 4th Seed
- Semifinal 2: 2nd Seed vs 3rd Seed
- Grand Finale: Winners of both semifinals face off
- Failing to adhere to the condition in Power Prompt Twist card impacts scoring under "Prompt Quality".
The scores for each of the teams are evaluated on the basis of the criteria decided, which includes Prompt Quality, LLM Interpretability, Deceptiveness, Opponent's guess, Clarity and Style, in case of a Tie, the team with higher LLM Interpretability score wins.
Event Heads
More Chaos
EVENT
CODERA
About the event
Codera is a fun and engaging competitive programming event that challenges your problem-solving skills, coding ability, and logical thinking through two exciting rounds.
EVENT
BOOM BOOM ROBO DA
About the event
Get ready for an action-packed technical treasure hunt that blends Computer Vision, IoT, puzzles, and DIY robotics into one thrilling challenge. Teams will navigate through multiple technical stations, solving challenges to earn robot components required for the final showdown. Each round tests problem-solving, observation, logical thinking, and teamwork, with every victory bringing teams one step closer to building their robot. The event culminates in a hands-on line-following robot race where speed, precision, and strategy determine the champion.
EVENT
WEBSITICA
About the event
WEBSITICA is a two-round web development event that challenges participants to combine creativity, technical expertise, and teamwork. Teams will design unconventional yet functional websites, solve interactive bonus challenges, and compete in communication-based UI recreation tasks. The event evaluates design, coding, strategy, memory, and collaboration in a fun and competitive environment.